Method and Electronic Device for Managing Artifacts of Image

1. A method for processing image data, the method comprising: receiving an input image; extracting a plurality of features from the input image, wherein the plurality of features comprise a texture of the input image, a color composition of the input image, and edges in the input image; determining at least one region of interest (RoI) in the input image including at least one artifact based on the plurality of features; generating at least one intermediate output image by removing the at least one artifact from the input image, using at least one of a first generative adversarial image generated by removing darkest regions of the at least one artifact in the input image, a second GAN image generated by removing at least one of color continuous regions or texture continuous regions of the at least one artifact in the input image, or a third GAN image generated by removing lightest regions of the at least one artifact and adding white patch regions to the at least one artifact in the input image; generating a binary mask directly from the at least one intermediate output image, the input image, the edges in the input image, and edges in the at least one intermediate output image; categorizing the at least one artifact into a first artifact category or a second artifact category, based on the binary mask; and obtaining a final output image by processing the input image based on a category of the at least one artifact corresponding to the first artifact category or the second artifact category.

2. The method as claimed in claim 1, further comprising: generating a plurality of versions of the at least one intermediate output image by varying a gamma value associated with the final output image; determining a naturalness image quality evaluator (NIQE) value for each of the plurality of versions of the at least one intermediate output image; and displaying, as the final output image, one of the plurality of versions of the at least one intermediate output image, which has a least NIQE value, among the NIQE values for the plurality of versions of the at least one intermediate output image.

3. The method as claimed in claim 1, wherein the extracting the plurality of features from the input image comprises: extracting the texture, the color composition, and the edges from the input image based on Otsu thresholding, Gaussian Blur and edge detection, respectively.

4. The method as claimed in claim 1, wherein a plurality of GANs are used to generate the least one the plurality of GANs comprise a negative generator, an artifact generator, a division generator, a negative discriminator, a division discriminator, a refinement generator and a refinement discriminator.

5. The method as claimed in claim 4, wherein the generating the at least one intermediate output image comprises: determining a set of loss values for each of the plurality of GANs; generating the first GAN image using the negative generator; generating the second GAN image using the artifact generator; generating the third GAN image using the division generator; and generating the at least one intermediate output image without the at least one artifact using at least one of the first GAN image, the second GAN image and the third GAN image.

6. The method as claimed in claim 1, wherein the input image is a previous input image, and the method further comprises: receiving a new input image; and overlaying the binary mask obtained for the previous input image on the new input image.

7. The method as claimed in claim 1, wherein the at least one artifact is a shadow or a glare.

8. The method as claimed in claim 1, wherein the first artifact category corresponds to a wanted artifact, and the second artifact category corresponds to an unwanted artifact.

9. An electronic device for processing image data, the electronic device comprising: a memory storing instructions; and a processor configured to execute the instructions to: receive an input image; extract a plurality of features from the input image, wherein the plurality of features comprise a texture of the input image, a color composition of the input image and edges in the input image; determine a region of interest (RoI) in the input image comprising at least one artifact based on the plurality of features; generate an at least one intermediate output image by removing the at least one artifact from the input image, using at least one of a first generative adversarial image generated by removing darkest regions of the at least one artifact in the input image, a second GAN image generated by removing at least one of color continuous regions or texture continuous regions of the at least one artifact in the input image, or a third GAN image generated by removing lightest regions of the at least one artifact and adding white patch regions to the at least one artifact in the input image; generate a binary mask directly from the at least one intermediate output image, the input image, the edges in the input image and edges in the at least one intermediate output image; categorize the at least one artifact into a first artifact category or a second artifact category, based on the binary mask; and obtain a final output image from the input image based on a category of the at least one artifact that corresponds to the first artifact category or the second artifact category.

10. The electronic device as claimed in claim 9, wherein the processor is further configured to: generate a plurality of versions of the at least one intermediate output image by varying a gamma value associated with the final output image; determine a naturalness image quality evaluator (NIQE) value for each of the plurality of versions of the at least one intermediate output image; and display a version of the final output image with a least NIQE value, among the NIQE values for the plurality of versions.

11. The electronic device as claimed in claim 9, wherein the processor is further configured to: extract the texture, the color composition, and the edges based on Otsu thresholding, Gaussian Blur, and edge detection, respectively.

12. The electronic device as claimed in claim 9, wherein a plurality of GANs are used to generate the least the plurality of GANs comprise a negative generator, an artifact generator, a division generator, a negative discriminator, a division discriminator, a refinement generator, and a refinement discriminator.

13. The electronic device as claimed in claim 12, wherein the processor is further configured to: determine a set of loss values for each of the plurality of GANs; generate the first GAN image using the negative generator; generate the second GAN image using the artifact generator; generate the third GAN image using the division generator; and generate the at least one intermediate output image without the at least one artifact using at least one of the first GAN image, the second GAN image and the third GAN image.

14. The electronic device as claimed in claim 9, wherein the input image is a previous input image, and the processor is further configured to: receive a new input image; and overlay the binary mask obtained for the previous input image on the new input image.

15. The electronic device as claimed in claim 9, wherein the at least one artifact is a shadow or a glare.

16. The electronic device as claimed in claim 9, wherein the first artifact category corresponds to a wanted artifact, and the second artifact category corresponds to an unwanted artifact.

17. A non-transitory computer-readable storage medium storing a program that is executable by one or more processors to perform a method of processing image data, the method comprising: obtaining an input image; identifying types of artifacts included in the input image, wherein the types of artifacts comprise a darkest region of a shadow in the input image, a continuous color and texture region of the shadow, and a lightest region of the shadow; generating a plurality of intermediate output images in which the artifacts by removing the darkest region of the shadow from the input image to generate a first intermediate output image, removing the continuous color and texture region of the shadow from the input image to generate a second intermediate output image, and removing the lightest region of the shadow from the input image to generate a third intermediate output image; generating a binary mask based on the plurality of intermediate output images and the input image; and applying the binary mask to the input image to selectively keep or remove the artifacts and to obtain a final output image in which at least one of the artifacts remains and another at least one of the artifacts is removed.

18. The non-transitory computer-readable storage medium of claim 17, wherein the removing the lightest region of the shadow to generate the third intermediate output image comprises: adding a white patch to the lightest region of the shadow after removing the lightest region of the shadow.

19. The non-transitory computer-readable storage medium of claim 17, wherein the method further comprises combining the first intermediate output image, the second intermediate output image, and the third intermediate output image, as a combined intermediate image of the plurality of intermediate output images; and wherein the generating the binary mask comprises generating the binary mask based on the combined intermediate image.